Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating summaries or collections of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourse
    -0.15
     Luca
    -0.15
    (machine
    -0.14
    ä¸įå¾Ĺ
    -0.14
    ë¶Ģ
    -0.14
     orm
    -0.14
    usses
    -0.13
    äs
    -0.13
    011
    -0.13
    335
    -0.13
    POSITIVE LOGITS
    erer
    0.18
    aghan
    0.18
    бÑĥÑĢг
    0.16
    uhan
    0.15
    ero
    0.15
     effected
    0.14
    िशत
    0.14
    vro
    0.14
    onde
    0.14
     exploits
    0.14
    Act Density 0.006%

    No Known Activations